Abstract | ||
---|---|---|
Existing approaches to contextual reasoning for enhanced object detection typically utilize other labeled categories in the images to provide contextual information. As a consequence, they inadvertently commit to the granularity of information implicit in the labels. Moreover, large portions of the images may not belong to any of the manually-chosen categories, and these unlabeled regions are typically neglected. In this paper, we overcome both these drawbacks and propose a contextual cue that exploits unlabeled regions in images. Our approach adaptively determines the granularity (scene, inter-object, intra-object, etc.) at which contextual information is captured. In order to extract the proposed contextual cue, we consider a scene to be a structured configuration of objects and regions; just as an object is a composition of parts. We thus learn our proposed “contextual meta-objects” using any off-the-shelf object detector, which makes our proposed cue widely accessible to the community. Our results show that incorporating our proposed cue provides a relative improvement of 12% over a state-of-the-art object detector on the challenging PASCAL dataset. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICCV.2011.6126282 | ICCV |
Keywords | Field | DocType |
approach adaptively,off-the-shelf object detector,contextual cue,adaptive contextual cues extraction,pascal dataset,proposed contextual cue,contextual information,enhanced object detection,adaptive contextual cue,state-of-the-art object detector,feature extraction,object detection,information granularity,proposed cue,unlabeled region,contextual meta-objects,context modeling,context model,detectors,data mining | Object detection,Computer vision,Pattern recognition,Computer science,Commit,Feature extraction,Context model,Exploit,Artificial intelligence,Granularity,Contextual image classification,Detector | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
ISBN | Citations | PageRank |
978-1-4577-1101-5 | 21 | 1.36 |
References | Authors | |
23 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Congcong Li | 1 | 240 | 16.48 |
Devi Parikh | 2 | 2929 | 132.01 |
Tsuhan Chen | 3 | 4763 | 346.32 |